BP Synthesis Data Set Construction

• DK created this script to combine older Ecodaat and EMA data, for newer data, these steps are done before they go into the database.
• SO, I am just going to keep the old data and cut on top the new data.

library(here)
library(tidyverse)
library(readxl)
# "RODBC", "here", "rnaturalearth", "rnaturalearthdata", "maps", "mapdata", "marmap", "rgdal")
 

Read in the EMA data files

BASIS_Zoo_1999_2004 <- read_xlsx(here( "data", "Raw-Data", "EMA-Historical-Data", "BASIS_Zoo_1999_2004.xlsx"), col_types = c("text", "text", "text", "numeric", "text", "numeric", "date", "date", "date", "numeric", "numeric", "text", "numeric", "numeric", "text", "text", "numeric", "text", "numeric", "text", "text", "text", "text", "numeric", "numeric", "numeric", "text", "text", "numeric", "numeric", "numeric", "numeric", "numeric", "numeric"))


BASIS_Zoo_2005_2009 <- read_xlsx (here("data", "Raw-Data", "EMA-Historical-Data", "BASIS_Zoo_2005_2009.xlsx"), col_types = c("text", "text", "text", "numeric", "text", "numeric", "date", "date", "date", "numeric", "numeric", "text", "numeric", "numeric", "text", "text", "numeric", "text", "numeric", "text", "text", "text", "text", "numeric", "numeric", "numeric", "text", "text", "numeric", "numeric", "numeric", "numeric", "numeric", "numeric"))

BASIS_Zoo_2010_2013 <- read_xlsx (here("data", "Raw-Data", "EMA-Historical-Data", "BASIS_Zoo_2010_2013.xlsx"), col_types = c("text", "text", "text", "numeric", "text", "numeric", "date", "date", "date", "numeric", "numeric", "text", "numeric", "numeric", "text", "text", "numeric", "text", "numeric", "text", "text", "text", "text", "numeric", "numeric", "numeric", "text", "text", "numeric", "numeric", "numeric", "numeric", "numeric", "numeric"))

BASIS_Zoo_2014_2017 <- read_xlsx (here("data", "Raw-Data", "EMA-Historical-Data", "BASIS_Zoo_2014_2017_LonCorrected.xlsx"), col_types = c("text", "text", "text", "numeric", "text", "numeric", "date", "date", "date", "numeric", "numeric", "text", "numeric", "numeric", "text", "text", "numeric", "text", "numeric", "text", "text", "text", "text", "numeric", "numeric", "numeric", "text", "text", "numeric", "numeric", "numeric", "numeric", "numeric", "numeric"))

EMA_Combined <- rbind(BASIS_Zoo_1999_2004, BASIS_Zoo_2005_2009, BASIS_Zoo_2010_2013, BASIS_Zoo_2014_2017)

rm(BASIS_Zoo_1999_2004, BASIS_Zoo_2005_2009, BASIS_Zoo_2010_2013, BASIS_Zoo_2014_2017)

Convert EMA fields into EcoDAAT fields

#Create DAY, MONTH, YEAR columns from "HaulDate"

EMA_Combined_Recode <-  EMA_Combined
 
EMA_Combined_Recode <- separate(EMA_Combined_Recode, HaulDate, c("YEAR", "MONTH", "DAY"), sep="-")

#Delete year column from the HaulID as there is already a year column

EMA_Combined_Recode$YEAR <- NULL
EMA_Combined_Recode <- rename(EMA_Combined_Recode, YEAR = Year)


#Extract Cruise code 
EMA_Combined_Recode$CRUISE <- substring (EMA_Combined_Recode$StationID, 5,6)

EMA_Combined_Recode$CRUISE_ID <- substring (EMA_Combined_Recode$StationID, 7,8)

#Recod Cruise code with ship ID and 

EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE == "01"] <- "SS"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE == "02"] <- "NWE"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE == "03"] <- "DY"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE == "04"] <- "GP"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE == "05"] <- "EE"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE == "06"] <- "HE"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE == "07"] <- "LU"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE == "08"] <- "BE"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE == "09"] <- "AE"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE == "10"] <- "JC"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE == "11"] <- "ST"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE == "12"] <- "CH"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE == "13"] <- "SA"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE == "14"] <- "QU"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE == "15"] <- "CF"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE == "16"] <- "OS"

#Get last two digits of year

EMA_Combined_Recode$CRUISE_YEAR <- substring (EMA_Combined_Recode$YEAR, 3,4)

#Combined CRUISE with 

EMA_Combined_Recode <- unite(EMA_Combined_Recode, "CRUISE", CRUISE, CRUISE_YEAR, sep="")

EMA_Combined_Recode <- unite(EMA_Combined_Recode, "CRUISE", CRUISE, CRUISE_ID, sep = "-")


#Count number of cruises in the EMA dataset

EMA_Combined_Recode_byCRUISE <- group_by(EMA_Combined_Recode, CRUISE)
EMA_Combined_Recode_CruiseCount <- summarise(EMA_Combined_Recode_byCRUISE, n_distinct(YEAR))

ungroup(EMA_Combined_Recode)

#Recode cruises to match nomenclature change in 2013 (i.e., 2DY12 becomes DY13-02 in 2013)

EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE=="BE11-01"] <- "1BE11"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE=="BE12-01"] <- "1BE12"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE=="DY07-02"] <- "2OD07"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE=="DY08-06"] <- "6DY08"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE=="DY09-05"] <- "5DY09"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE=="DY10-04"] <- "4DY10"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE=="DY11-04"] <- "4DY11"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE=="DY12-03"] <- "3DY12"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE=="EE09-01"] <- "1EE09"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE=="EE10-01"] <- "1EE10"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE=="GP00-01"] <- "1GP00"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE=="GP99-01"] <- "1GP99"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE=="NWE06-01"] <- "1NW06"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE=="SS02-01"] <- "1SS02"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE=="SS03-01"] <- "1SS03"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE=="SS04-01"] <- "1SS04"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE=="SS05-01"] <- "1SS05"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE=="SS06-01"] <- "1SS06"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE=="SS07-01"] <- "1SS07"
EMA_Combined_Recode$CRUISE[EMA_Combined_Recode$CRUISE=="NWE17-05"] <- "NW17-05"

#Remove a few files

rm(EMA_Combined_Recode_byCRUISE, EMA_Combined_Recode_CruiseCount)


#Rename Abundance to EST_NUM_PERM3

EMA_Combined_Recode <- rename(EMA_Combined_Recode, EST_NUM_PERM3 = Abundance)

#Rename GearDepth to MAX_GEAR_DEPTH and use to calculate EST_NUM_PERM3

EMA_Combined_Recode <- rename(EMA_Combined_Recode, MAX_GEAR_DEPTH = GearDepth)

#Compute EST_NUM_PERM2 = EST_NUM_PERM3 * MAX_GEAR_DEPTH

EMA_Combined_Recode$EST_NUM_PERM2 <- EMA_Combined_Recode$EST_NUM_PERM3*EMA_Combined_Recode$MAX_GEAR_DEPTH

#Create columns GEAR_NAME, MESH from GearCode column

EMA_Combined_Recode$GearCode[EMA_Combined_Recode$GearCode == "Bongo153"] <- "20BON_153"
EMA_Combined_Recode$GearCode[EMA_Combined_Recode$GearCode == "Bongo333"] <- "60BON_333"
EMA_Combined_Recode$GearCode[EMA_Combined_Recode$GearCode == "Bongo505"] <- "60BON_505"
EMA_Combined_Recode$GearCode[EMA_Combined_Recode$GearCode == "Bongo80"] <- "80BON_153"
EMA_Combined_Recode$GearCode[EMA_Combined_Recode$GearCode == "Juday"] <- "Juday_168"
EMA_Combined_Recode$GearCode[EMA_Combined_Recode$GearCode == "PairoVET"] <- "PairoVET_153"

EMA_Combined_Recode <- separate(EMA_Combined_Recode, GearCode, c("GEAR_NAME", "MESH"), sep = "_")

#Rename GearInTime to GMT_DATE_TIME_TXT

EMA_Combined_Recode <- rename(EMA_Combined_Recode, GMT_DATE_TIME_TXT = GearInTime)
  
#Rename Quality to HAUL_PERFORMANCE and recode to match EcoDAAT 

EMA_Combined_Recode <- rename(EMA_Combined_Recode, HAUL_PERFORMANCE = Quality)

EMA_Combined_Recode$HAUL_PERFORMANCE[EMA_Combined_Recode$HAUL_PERFORMANCE == "G"] <- "GOOD"
EMA_Combined_Recode$HAUL_PERFORMANCE[EMA_Combined_Recode$HAUL_PERFORMANCE == "Q"] <- "QUEST"

#Create LAT and LON column from GearInLatitude and Gear in Longitude

EMA_Combined_Recode <- rename(EMA_Combined_Recode, LAT = GearInLatitude)

EMA_Combined_Recode <- rename(EMA_Combined_Recode, LON = GearInLongitude)

#Create column SEX_NAME from Sex and recode to match EcoDAAT categories

EMA_Combined_Recode <- rename(EMA_Combined_Recode, SEX_NAME = Sex)

EMA_Combined_Recode$SEX_NAME[EMA_Combined_Recode$SEX_NAME == "M"] <- "MALE"
EMA_Combined_Recode$SEX_NAME[EMA_Combined_Recode$SEX_NAME == "F"] <- "FEMALE"
EMA_Combined_Recode$SEX_NAME[EMA_Combined_Recode$SEX_NAME == "U"] <- "NOT DETERMINED"

#EMA Size categories are numerous, so keep this column, but rename as SIZE_NAME for merging

EMA_Combined_Recode <- rename(EMA_Combined_Recode, SIZE_NAME = Size)

#Create STAGE_NAME category by renaming "StageCode" and recoding

EMA_Combined_Recode <- rename(EMA_Combined_Recode, STAGE_NAME = StageCode)

EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "A"] <- "ADULT"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "A & J"] <- "A + J (ADULT/JUVENILE)"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "adult"] <- "ADULT"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "Adult"] <- "ADULT"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "C1"] <- "C - 1 (COPEPODITE I)"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "C1-2"] <- "C-1 TO C-2"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "C1-3"] <- "C-1 TO C-3"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "C1-4"] <- "C-1 TO C-4"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "C1-5"] <- "C-1 TO C-5"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "C1-C4"] <- "C-1 TO C-4"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "C2"] <- "C - 2 (COPEPODITE II)"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "C2-C3"] <- "C-2 TO C-3"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "C2-C5"] <- "C-2 TO C-5"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "C3"] <- "C - 3 (COPEPODITE III)"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "C3-C4"] <- "C-3 TO C-4"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "C3-C5"] <- "C-3 TO C-5"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "C4"] <- "C - 4 (COPEPODITE IV)"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "C4-C5"] <- "C-4 TO C-5"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "C4-C6"] <- "C-4 TO C-6"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "C5"] <- "C - 5 (COPEPODITE V)"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "C6"] <- "ADULT"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "calyptopis"] <- "CALYPTOPIS (STAGE NOT DETERMINED)"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "calyptopis 1"] <- "CALYPTOPIS (STAGE NOT DETERMINED)"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "calyptopis 2"] <- "CALYPTOPIS (STAGE NOT DETERMINED)"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "calyptopis 3"] <- "CALYPTOPIS (STAGE NOT DETERMINED)"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "cypris"] <- "CYPRIS"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "Cypris"] <- "CYPRIS"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "egg"] <- "EGG"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "Egg"] <- "EGG"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "furcilia"] <- "FURCILIA"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "Furcilia"] <- "FURCILIA"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "J"] <- "JUVENILE"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "juvenile"] <- "JUVENILE"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "Juvenile"] <- "JUVENILE"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "larva"] <- "LARVA"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "Larva"] <- "LARVA"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "larval"] <- "LARVA"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "Larval"] <- "LARVA"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "medusa"] <- "MEDUSA"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "Medusa"] <- "MEDUSA"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "megalopa"] <- "MEGALOPAE"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "Megalopa"] <- "MEGALOPAE"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "nauplius"] <- "NAUPLIUS"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "Nauplius"] <- "NAUPLIUS"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "ND"] <- "NOT DETERMINED"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "post-larva"] <- "POST LARVA"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "U"] <- "NOT DETERMINED"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "zoea"] <- "ZOEA"
EMA_Combined_Recode$STAGE_NAME[EMA_Combined_Recode$STAGE_NAME == "Zoea"] <- "ZOEA"

#Create Column STATION_NAME by using the last 3 digits of StationID

EMA_Combined_Recode$STATION_NAME<- substring (EMA_Combined_Recode$StationID, 9,11)

#Create TAXON_NAME column and recode to match EcoDAAT

EMA_Combined_Recode <- rename(EMA_Combined_Recode, TAXON_NAME = Current_Name)

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Acanthomysis sp."] <- "Acanthomysis spp."

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Acanthomysis stelleri"] <- "Acanthomysis stelleri (Exacanthomysis arctopacifica)"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Anthoathecatae"] <- "Anthoathecata (Anthomedusae)"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Cancridae"] <- "Cancridae (Brachyura)"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Candacia columbiae"] <- "Candacia Columbiae"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Caprellidea"] <- "Caprellidae"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Clytia gregaria"] <- "Clytia gregaria (Phialidium gregarium)"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Cnidaria"] <- "Cnidarian medusae"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Corophium spp."] <- "Corophium"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Disacanthomysis dybowskii"] <- "Discanthomysis (Acanthomysis) Dybowskii"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Epilabidocera amphitrites"] <- "Epilabidocera amphitrites (E. longipedata)"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Epilabidocera longipedata"] <- "Epilabidocera amphitrites (E. longipedata)"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Euphausia spp."] <- "Euphausiacea"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Eurytemora pacifica"] <- "Eurytemora pacifica (E. johanseni)"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Eurytemora sp."] <- "Eurytemora spp."

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Gammaridae"] <- "Gammaridea (Unidentifiable)"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Gammaridea"] <- "Gammaridea (Unidentifiable)"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Hippolytidae"] <- "Hippolytidae (Caridea)"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Hydromedusae (Hydroidolina"] <- "Hydromedusae"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Leptothecatae"] <- "Leptothecata (Leptomedusae)"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Lithodidae"] <- "Lithodidae (Anomura)"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Majidae"] <- "Majidae (Brachyura)"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Meterythrops robusta"] <- "Meterythrops robustus (M. robusta)"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Mysida"] <- "Mysida (Unidentifiable)"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Octopoda"] <- "Octopodiformes (Octopus) larvae"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Oithona setigera"] <- "Oithona setigera (O. spinirostris)"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Oithona spinirostris"] <- "Oithona setigera (O. spinirostris)"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Chionoecetes spp."] <- "Oregoniidae (Brachyura)"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Hyas spp."] <- "Oregoniidae (Brachyura)"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Oregoniidae"] <- "Oregoniidae (Brachyura)"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Pacifacanthomysis nephrophthalma"] <- "Pacifacanthomysis (Acanthomysis) nephrophthalma"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Paguridae"] <- "Paguridae (Anomura)"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Paraeuchaeta elongata"] <- "Paraeuchaeta elongata (Euchaeta elongata)"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Parasagitta elegans"] <- "Parasagitta (Sagitta) elegans"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Phoronida (actinotroch larva)"] <- "Phoronida actinotroch (larvae)"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Podon leuckartii"] <- "Podon leuckarti"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Pseudoamallothrix ovata"] <- "Pseudoamallothrix (scolecithricella) ovata"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Syrrhoe"] <- "Syrrhoe spp."

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Tessarabrachion oculatus"] <- "Tessarabrachion oculatum"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Thecosomata"] <- "Thecosomata (Unidentifiable)"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Themisto pacifica"] <- "Themisto pacifica (Parathemisto pacifica)"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Triconia sp."] <- "Triconia spp."

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Calanidae"] <- "Unidentified Calanids"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Calanoida"] <- "Unidentified Calanids"

EMA_Combined_Recode$TAXON_NAME[EMA_Combined_Recode$TAXON_NAME == "Xenacanthomysis pseudomacropsis"] <- "Xenoacanthomysis (Acanthomysis) pseudomacropsis"



#Create VOLUME_FILTERED column by renaming TowVOlume column

EMA_Combined_Recode <- rename(EMA_Combined_Recode, VOLUME_FILTERED = TowVolume)

#Rename BottomDepth to BOTTOM_DEPTH to match EcoDAAT

EMA_Combined_Recode <- rename(EMA_Combined_Recode, BOTTOM_DEPTH = BottomDepth)


#Rearrange the file to add a column indicating origin of data, to have them in the same order as the EcoDAAT file and remove non-matched columns prior to merge


EMA_Combined_Recode$DATA_SOURCE <- "EMA"

#Inset columns not present in EMA, but will be in EcoDAAT

EMA_Combined_Recode$DIS_PERVOLM2 <- NA
EMA_Combined_Recode$DIS_PERVOLM3 <- NA
EMA_Combined_Recode$FOCI_ID <- NA
EMA_Combined_Recode$FOCI_SAMPLE_ID <- NA
EMA_Combined_Recode$GEOGRAPHIC_AREA <- NA
EMA_Combined_Recode$HAUL_ID <- NA
EMA_Combined_Recode$HAUL_NAME <- NA
EMA_Combined_Recode$MIN_GEAR_DEPTH <- NA
EMA_Combined_Recode$NET <- NA
EMA_Combined_Recode$SAMPLE_DEPTH <- NA
EMA_Combined_Recode$SEX <- NA
EMA_Combined_Recode$SPECIMEN_FORM <- NA
EMA_Combined_Recode$STAGE <- NA
EMA_Combined_Recode$TAXON_SIZE <- NA
EMA_Combined_Recode$ZOOP_COPEPOD_NAUPLII <- NA
EMA_Combined_Recode$ZOOP_EUPHAUSIID_EGG <- NA


#Create HAUL_ID column information for merging purposes

EMA_Combined_Recode$HAUL_ID <- paste0(EMA_Combined_Recode$CRUISE," ",EMA_Combined_Recode$STATION_NAME," ", 1," ", EMA_Combined_Recode$GEAR_NAME," ", 1)


#Create vector of column names from the EcoDAAT File

EcoDAAT_ColumnNames <- c("BOTTOM_DEPTH", "CRUISE", "DAY", "DIS_PERVOLM2", "DIS_PERVOLM3", "EST_NUM_PERM2", "EST_NUM_PERM3", "FOCI_ID", "FOCI_SAMPLE_ID", "GEAR_NAME", "GEOGRAPHIC_AREA", "GMT_DATE_TIME_TXT", "HAUL_ID", "HAUL_NAME", "HAUL_PERFORMANCE", "LAT", "LON", "MAX_GEAR_DEPTH", "MESH", "MIN_GEAR_DEPTH", "MONTH", "NET", "SAMPLE_DEPTH", "SEX", "SEX_NAME", "SIZE_NAME", "SPECIMEN_FORM", "STAGE", "STAGE_NAME", "STATION_NAME", "TAXON_NAME", "TAXON_SIZE", "VOLUME_FILTERED",  "YEAR", "ZOOP_COPEPOD_NAUPLII", "ZOOP_EUPHAUSIID_EGG", "DATA_SOURCE")

EMA_Combined_Recode <- EMA_Combined_Recode[, EcoDAAT_ColumnNames]

Import EcoDAAT data

Connect to database to import zoop data directly from EcoDAAT

#Create connect to the AFSC database
# 
# user <- readline("Input Username: ")
# pswd <- readline("Input Password: ")
# 
# AFSC_Connect <- odbcConnect("AFSC", uid=user,  pwd=pswd)
# 
# 
# #Delete and refresh table to draw from, in this case it is SPECIMEN_MAIN_GEOM
# 
# sqlQuery(AFSC_Connect,"DROP TABLE SPECIMEN_MAIN_GEOM;")
# 
# sqlQuery(AFSC_Connect,"CREATE TABLE SPECIMEN_MAIN_GEOM AS SELECT * FROM ECODAAT.SPECIMEN_MAIN_GEOM;")


#Run SQL Queries to build zooplankton dataset 
# 
# #Query the database
# 
# zoopdata <- sqlQuery(AFSC_Connect, "SELECT BOTTOM_DEPTH,
# CRUISE, DAY, DIS_PERVOLM2, DIS_PERVOLM3, EST_NUM_PERM2, EST_NUM_PERM3, FOCI_ID, FOCI_SAMPLE_ID, GEAR_NAME, 
# GEOGRAPHIC_AREA, GMT_DATE_TIME_TXT, HAUL_ID, HAUL_NAME, HAUL_PERFORMANCE, LAT, LON, MAX_GEAR_DEPTH, MESH,
# MIN_GEAR_DEPTH, MONTH, NET, SAMPLE_DEPTH, SEX, SEX_NAME, SIZE_NAME, SPECIMEN_FORM, STAGE, STAGE_NAME, STATION_NAME,
# TAXON_NAME, TAXON_SIZE, VOLUME_FILTERED, YEAR, ZOOP_COPEPOD_NAUPLII, ZOOP_EUPHAUSIID_EGG
# FROM SPECIMEN_MAIN_GEOM WHERE ORIG_DB LIKE 'BOB';", stringsAsFactors=FALSE)

#Close database connection
 
# odbcClose(AFSC_Connect)

#Drop one cruise using the old protocol OS17 and replace with correct data
zoopdata <- read_csv(here("data","AllZoopRaw.csv")) %>%
  filter(!CRUISE=="OS17-01") %>%
  dplyr::select(-...1)

New names:
• `` -> `...1`
Rows: 825071 Columns: 37
── Column specification ───────────────────────────────────────────────────────────────
Delimiter: ","
chr  (15): CRUISE, FOCI_ID, FOCI_SAMPLE_ID, GEAR_NAME, GEOGRAPHIC_AREA, HAUL_ID, HA...
dbl  (21): ...1, BOTTOM_DEPTH, DAY, DIS_PERVOLM2, DIS_PERVOLM3, EST_NUM_PERM2, EST_...
dttm  (1): GMT_DATE_TIME_TXT

ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

#Bring in OS17-01
OS1701 <- read.csv(here("data", "Raw-Data", "OS1701_EcoFOCI_ZooplanktonNet.csv"))

zoopdata <- rbind(zoopdata, OS1701)

#Delete OS1701

rm(OS1701)

Do some data tidying for the EcoDAAT data set and combine the EcoDAAT and EMA datasets

#Recode mesh sizes for 150, 333, 500

zoopdata$MESH[zoopdata$MESH==150] <- 153
zoopdata$MESH[zoopdata$MESH==154] <- 153
zoopdata$MESH[zoopdata$MESH==1153] <- 153
zoopdata$MESH[zoopdata$MESH==335] <- 333
zoopdata$MESH[zoopdata$MESH==500] <- 505


#Count number of cruises in the EMA dataset

EMA_Combined_Recode_byCRUISE <- group_by(EMA_Combined_Recode, CRUISE)
EMA_Combined_Recode_CruiseCount <- summarise(EMA_Combined_Recode_byCRUISE, n_distinct(YEAR))

ungroup(EMA_Combined_Recode)

#Count number of cruises in the EMA dataset

zoopdata_byCRUISE <- group_by(zoopdata, CRUISE)
zoopdata_CruiseCount <- summarise(zoopdata_byCRUISE, n_distinct(YEAR))

ungroup(zoopdata)

 

#Do a join to see if cruises have matches in both datasets:

TestData <- semi_join(EMA_Combined_Recode_CruiseCount, zoopdata_CruiseCount, by = "CRUISE")




#10 cruises are present in EMA dataset and zoopdata data set, remove those from the EMA dataset to avoid double counting

EMA_Combined_Recode <- filter(EMA_Combined_Recode, CRUISE!="1GP99")
EMA_Combined_Recode <- filter(EMA_Combined_Recode, CRUISE!="3DY12")
EMA_Combined_Recode <- filter(EMA_Combined_Recode, CRUISE!="AE14-01")
EMA_Combined_Recode <- filter(EMA_Combined_Recode, CRUISE!="AE15-01")
EMA_Combined_Recode <- filter(EMA_Combined_Recode, CRUISE!="DY14-06")
EMA_Combined_Recode <- filter(EMA_Combined_Recode, CRUISE!="DY14-08")
EMA_Combined_Recode <- filter(EMA_Combined_Recode, CRUISE!="DY15-07")
EMA_Combined_Recode <- filter(EMA_Combined_Recode, CRUISE!="DY15-08")
EMA_Combined_Recode <- filter(EMA_Combined_Recode, CRUISE!="DY16-09")
EMA_Combined_Recode <- filter(EMA_Combined_Recode, CRUISE!="NW17-05")

#RemoveFiles

rm(EMA_Combined_Recode_byCRUISE, EMA_Combined_Recode_CruiseCount, zoopdata_byCRUISE, zoopdata_CruiseCount, TestData)

#Combine the EMA and EcoDAAT datasets

#Add Data Source file to the zoopdata prior to combination

zoopdata$DATA_SOURCE <- "EcoDAAT"


#Combine datasets 

AllZoop_Raw <- rbind(EMA_Combined_Recode, zoopdata)



#Create vector of Combined column names to trim dataset for final processing

Combined_ColumnNames <- c("BOTTOM_DEPTH", "CRUISE", "DAY", "DIS_PERVOLM2", "DIS_PERVOLM3", "EST_NUM_PERM2", "EST_NUM_PERM3", "GEAR_NAME", "GMT_DATE_TIME_TXT", "HAUL_ID", "HAUL_PERFORMANCE", "LAT", "LON", "MAX_GEAR_DEPTH", "MESH", "MONTH", "SPECIMEN_FORM", "SEX_NAME", "SIZE_NAME", "STAGE_NAME", "STATION_NAME", "TAXON_NAME", "VOLUME_FILTERED",  "YEAR", "DATA_SOURCE")

#Keep only those columns

AllZoop_Raw <- AllZoop_Raw[,Combined_ColumnNames]

#Remove files

rm (EMA_Combined, EMA_Combined_Recode, zoopdata)

Quick map of the raw data stations

#Quick plot to take a look at the dataset so far

#Get world data from #natural earth package

world <- ne_countries(scale = "medium", returnclass = "sf")
class(world)

# get regional polygons
reg = map_data("world2Hires")
reg = subset(reg, region %in% c('USSR', 'USA'))

# convert lat longs
reg$long = (360 - reg$long)*-1

# set map limits
lons = c(-179.5, -130)
lats = c(50, 74)


######################################
# 
# # make plot
# Region_Map_RawData <- ggplot()+
# 
#   # add coastline
#   geom_sf(data = world)+
#     coord_sf(xlim = lons, ylim = lats, expand = FALSE)+
# 
#   #Plot station points
#   geom_point(data=AllZoop_Raw, mapping=aes(LON, LAT))+
# 
#   # formatting
#   theme_bw()+
#   xlab("Longitude")+
#   ylab("Latitude")
# 
# Region_Map_RawData

Data Filtering for BP Synthesis Project

#First filter for all data north of 60N
       
#
NBS_Zoop <- filter(AllZoop_Raw, LAT>=55)


#Now map again to take a look
# 
# # make plot
# Region_Map_NBS_Process_1 <- ggplot()+
# 
#   # add coastline
#   geom_sf(data = world)+
#     coord_sf(xlim = lons, ylim = lats, expand = FALSE)+
# 
#   #Plot station points
#   geom_point(data=NBS_Zoop, mapping=aes(LON, LAT))+
# 
#   # formatting
#   theme_bw()+
#   xlab("Longitude")+
#   ylab("Latitude")
# 
# Region_Map_NBS_Process_1
# 
# 
# #Looks like some data from the GOA is still present, so remove data > 155

#
NBS_Zoop <- filter(NBS_Zoop, LON<= -150)

#Now map again to take a look
# 
# # make plot
# Region_Map_NBS_Process_2 <- ggplot()+
# 
#   # add coastline
#   geom_sf(data = world)+
#     coord_sf(xlim = lons, ylim = lats, expand = FALSE)+
# 
#   #Plot station points
#   geom_point(data=NBS_Zoop, mapping=aes(LON, LAT))+
# 
#   # formatting
#   theme_bw()+
#   xlab("Longitude")+
#   ylab("Latitude")
# 
# Region_Map_NBS_Process_2
# 
# #Spatial coverage looks correct

#Now check temporal coverage

sort(unique(NBS_Zoop$YEAR), decreasing = FALSE)

 [1] 1987 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003
[17] 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019

#Remove data from 1996 as it is removed from all other years of collection

NBS_Zoop <- filter(NBS_Zoop, YEAR!=1996)

#Take a look at the gears present in the dataset

unique(NBS_Zoop$GEAR_NAME)

 [1] "60BON"    "Juday"    "PairoVET" "80BON"    "20BON"    "TUCK1"    "SLED"    
 [8] "LG-CB"    "V60BON"   "MBT"      "MOC1"     "CALVET"   "CTDB"     "METH"    
[15] "QUADNET"  "IKMT"    

unique(NBS_Zoop$MESH)

 [1] "505"  "333"  "168"  "153"  "3000" "1000" "53"   NA     "0"    "1500" "6000"

#Rough estimate of number of samples by gear type

NBS_Zoop_Gear <- NBS_Zoop[, c("CRUISE", "GEAR_NAME", "MESH", "LAT", "LON")]

NBS_Zoop_Gear <- distinct(NBS_Zoop_Gear)

NBS_Zoop_Gear_byGear <- group_by(NBS_Zoop_Gear, GEAR_NAME, MESH)

NBS_Gear_Summary <- summarise(NBS_Zoop_Gear_byGear, n())

`summarise()` has grouped output by 'GEAR_NAME'. You can override using the `.groups`
argument.

ungroup(NBS_Zoop_Gear)

#This shows a few gears can be eliminated for low sample size (V60BON, 80BON) and CALVET has too small mesh size

NBS_Zoop <- filter(NBS_Zoop, GEAR_NAME!="CALVET")
NBS_Zoop <- filter(NBS_Zoop, GEAR_NAME!="V60BON")
NBS_Zoop <- filter(NBS_Zoop, GEAR_NAME!="80BON")

#Remove sled data as this is biased toward a bottom sample

NBS_Zoop <- filter(NBS_Zoop, GEAR_NAME!="SLED")



#Remove failed and questionable hauls

#First save the NA since EMA data does not always record HAUL_PERFORMANCE

HaulPerf_NA <- NBS_Zoop[is.na(NBS_Zoop$HAUL_PERFORMANCE),]

NBS_Zoop_GOOD <- filter(NBS_Zoop, HAUL_PERFORMANCE=="GOOD")

#Rebuild dataset without QUEST and FAIL HAULS

NBS_Zoop <- rbind(HaulPerf_NA, NBS_Zoop_GOOD)



#Write this raw file prior to further processing

write.csv(NBS_Zoop, here("data", "Raw-Data", "NBS_Zoop_Raw.csv"))

Bring in the Coarse Taxa List to aid in lumping and filter out some taxa

TaxaList_Coarse <- read.csv(here("data", "Taxa-Lists", "TaxaList_Coarse.csv"))

#Now add this to the file

TaxaList_Coarse <- distinct(TaxaList_Coarse)

NBS_Zoop_Process <- left_join(NBS_Zoop, TaxaList_Coarse, by = "TAXON_NAME")

#Filter out those data marked for removal

NBS_Zoop_Process <- filter(NBS_Zoop_Process, NOTE != "Remove")

Create taxa specific data sets to select the correct stages from the correct GEAR_NAME and MESH for each specific coarse taxa

Acartia spp

Acartia_spp <- filter(NBS_Zoop_Process, TAXA_COARSE=="Acartia spp.")

#Acartia is a small copepod, so all estimates should come from the smaller nets

#Filter for correct gear

Acartia_spp <- filter(Acartia_spp, GEAR_NAME!= "60BON")


#Being to build final data set


NBS_Zoop_Process_Final <- Acartia_spp

Aglantha digitale

Aglantha_digitale <- filter(NBS_Zoop_Process, TAXA_COARSE=="Aglantha digitale")

#Choose to estimate Cnidarians from the 60BON only

Aglantha_digitale <- filter(Aglantha_digitale, GEAR_NAME=="60BON")


#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Aglantha_digitale)

Amphipods

Amphipoda <- filter(NBS_Zoop_Process, TAXA_COARSE=="Amphipoda")

#Amhipods will be estimated from the 60BON only

Amphipoda <- filter(Amphipoda, GEAR_NAME=="60BON")


#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Amphipoda)

Anomura

Anomura <- filter(NBS_Zoop_Process, TAXA_COARSE=="Anomura")

#Anomura estimate from 60BON only

Anomura <- filter(Amphipoda, GEAR_NAME=="60BON")

#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Anomura)

Appendicularia

Appendicularia <- filter(NBS_Zoop_Process, TAXA_COARSE=="Appendicularia")

#Can filter for both gears and then add a taxa coarse of Appendicularia_large and Appendicular_small

Appendicularia_large <- filter(Appendicularia, GEAR_NAME=="60BON")

#Recode coarse taxa

Appendicularia_large$TAXA_COARSE[Appendicularia_large$TAXA_COARSE=="Appendicularia"] <- "Appendicularia_large"


Appendicularia_small <- filter(Appendicularia, GEAR_NAME!="60BON")

#Recode coarse taxa

Appendicularia_small$TAXA_COARSE[Appendicularia_small$TAXA_COARSE=="Appendicularia"] <- "Appendicularia_small"


#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Appendicularia_large, Appendicularia_small)

Bivalvia

Bivalvia <- filter(NBS_Zoop_Process, TAXA_COARSE=="Bivalvia")

#Bivalvia estimate from smaller nets only

Bivalvia <- filter(Bivalvia, GEAR_NAME!="60BON")


#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Bivalvia)

Brachyura

Brachyura <- filter(NBS_Zoop_Process, TAXA_COARSE=="Brachyura")

#Brachyura estimate from 60BON only

Brachyura <- filter(Brachyura, GEAR_NAME=="60BON")

#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Brachyura)

Calanus hyperboreus

Calanus_hyperboreus <- filter(NBS_Zoop_Process, TAXA_COARSE=="Calanus hyperboreus")


#Separate EMA data as they were sorted under different protocols

Calanus_hyperboreus_EMA <- filter(Calanus_hyperboreus, DATA_SOURCE=="EMA")
Calanus_hyperboreus_EcoDAAT <- filter(Calanus_hyperboreus, DATA_SOURCE=="EcoDAAT")

#Check to see if right stages are in the EcoDAAT data

Calanus_hyperboreus_EcoDAAT_bySPECIMEN_FORM <- group_by(Calanus_hyperboreus_EcoDAAT, SPECIMEN_FORM, MESH, GEAR_NAME)

Calanus_hyperboreus_EcoDAAT_FormSummary <- summarise(Calanus_hyperboreus_EcoDAAT_bySPECIMEN_FORM,n())

`summarise()` has grouped output by 'SPECIMEN_FORM', 'MESH'. You can override using
the `.groups` argument.

#These look correct

#Now filter the EMA data to match the EcoDAAT data. EMA tends to double count variables from both nets, so eliminate this

#Check to see if what stages are where with EMA data

Calanus_hyperboreus_EMA_byGEAR_NAME <- group_by(Calanus_hyperboreus_EMA, MESH, GEAR_NAME)

Calanus_hyperboreus_EMA_GearSummary <- summarise(Calanus_hyperboreus_EMA_byGEAR_NAME, n())

`summarise()` has grouped output by 'MESH'. You can override using the `.groups`
argument.

#No issues with mismatched mesh and gear sizes. Need to filter for the correct stages for avoid double counts

Calanus_hyperboreus_EMA <- filter(Calanus_hyperboreus_EMA, MESH != 153)


#The other gears are correct, so rebuild dataset

Calanus_hyperboreus <- rbind(Calanus_hyperboreus_EcoDAAT, Calanus_hyperboreus_EMA)


#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Calanus_hyperboreus)

Calanus marshallae/glacialis

Calanus <- filter(NBS_Zoop_Process, TAXA_COARSE=="Calanus marshallae/glacialis")

#Separate EMA data as they were sorted under different protocols

Calanus_EMA <- filter(Calanus, DATA_SOURCE=="EMA")
Calanus_EcoDAAT <- filter(Calanus, DATA_SOURCE=="EcoDAAT")

#Check to see if right stages are in the EcoDAAT data

Calanus_EcoDAAT_bySPECIMEN_FORM <- group_by(Calanus_EcoDAAT, SPECIMEN_FORM, MESH, GEAR_NAME)

Calanus_EcoDAAT_FormSummary <- summarise(Calanus_EcoDAAT_bySPECIMEN_FORM,n())

`summarise()` has grouped output by 'SPECIMEN_FORM', 'MESH'. You can override using
the `.groups` argument.

#Do some filtering to get the correct stages from the correct gear for EcoDAAT data

Calanus_EcoDAAT_B <- filter(Calanus_EcoDAAT, SPECIMEN_FORM=="B")
Calanus_EcoDAAT_B <- filter(Calanus_EcoDAAT_B, MESH!=153)

Calanus_EcoDAAT_C <- filter(Calanus_EcoDAAT, SPECIMEN_FORM=="C")
Calanus_EcoDAAT_C <- filter(Calanus_EcoDAAT_C, MESH==153)
Calanus_EcoDAAT_C <- filter(Calanus_EcoDAAT_C, GEAR_NAME=="20BON")

Calanus_EcoDAAT_G <- filter(Calanus_EcoDAAT, SPECIMEN_FORM=="G")

Calanus_EcoDAAT_H <- filter(Calanus_EcoDAAT, SPECIMEN_FORM=="H")

Calanus_EcoDAAT_K <- filter(Calanus_EcoDAAT, SPECIMEN_FORM=="K")

Calanus_EcoDAAT_L <- filter(Calanus_EcoDAAT, SPECIMEN_FORM=="L")

#The other gears are correct, so rebuild dataset

Calanus_EcoDAAT_Final <- rbind(Calanus_EcoDAAT_B, Calanus_EcoDAAT_C, Calanus_EcoDAAT_G, Calanus_EcoDAAT_H, Calanus_EcoDAAT_K, Calanus_EcoDAAT_L)

ungroup(Calanus_EcoDAAT_Final)

#Remove some files

rm(Calanus_EcoDAAT_bySPECIMEN_FORM, Calanus_EcoDAAT_B, Calanus_EcoDAAT_C, Calanus_EcoDAAT_G, Calanus_EcoDAAT_H, Calanus_EcoDAAT_K, Calanus_EcoDAAT_L)

#Now filter the EMA data to match the EcoDAAT data. EMA tends to double count variables from both nets, so eliminate this

#Check to see if what stages are where with EMA data

Calanus_EMA_byGEAR_NAME <- group_by(Calanus_EMA, MESH, GEAR_NAME)

Calanus_EMA_GearSummary <- summarise(Calanus_EMA_byGEAR_NAME, n())

`summarise()` has grouped output by 'MESH'. You can override using the `.groups`
argument.

#No issues with mismatched mesh and gear sizes. Need to filter for the correct stages for avoid double counts

Calanus_EMA_60BON <- filter(Calanus_EMA, GEAR_NAME=="60BON")

Calanus_EMA_60BON_333 <- filter(Calanus_EMA_60BON, MESH==333)

Calanus_EMA_60BON_333 <- filter(Calanus_EMA_60BON_333, STAGE_NAME=="ADULT"|STAGE_NAME=="C - 5 (COPEPODITE V)"|STAGE_NAME=="C - 4 (COPEPODITE IV)"|STAGE_NAME=="C - 3 (COPEPODITE III)")

Calanus_EMA_60BON_505 <- filter(Calanus_EMA_60BON, MESH==505)

Calanus_EMA_60BON_505 <- filter(Calanus_EMA_60BON_505, STAGE_NAME=="ADULT"|STAGE_NAME=="C - 5 (COPEPODITE V)"|STAGE_NAME=="C - 4 (COPEPODITE IV)")

Calanus_EMA_20BON <- filter(Calanus_EMA, GEAR_NAME=="20BON")

Calanus_EMA_20BON_153 <- filter(Calanus_EMA_20BON, MESH==153)

Calanus_EMA_20BON_153 <- filter(Calanus_EMA_20BON_153, STAGE_NAME=="C - 2 (COPEPODITE II)"|STAGE_NAME=="C - 1 (COPEPODITE I)")

#The other gears are correct, so rebuild dataset

Calanus_EMA_Final <- rbind(Calanus_EMA_60BON_333, Calanus_EMA_60BON_505, Calanus_EMA_20BON_153)

ungroup(Calanus_EMA_Final)

#Remove some files

rm(Calanus_EMA_byGEAR_NAME, Calanus_EMA_20BON, Calanus_EMA_20BON_153, Calanus_EMA_60BON, Calanus_EMA_60BON_333, Calanus_EMA_60BON_505)

#Combine into final, Calanus data set

Calanus <- rbind(Calanus_EMA_Final, Calanus_EcoDAAT_Final)

#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Calanus)

Calanus pacificus

Calanus_pacificus <- filter(NBS_Zoop_Process, TAXA_COARSE == "Calanus pacificus")


#Separate EMA data as they were sorted under different protocols

Calanus_pacificus_EMA <- filter(Calanus_pacificus, DATA_SOURCE=="EMA")
Calanus_pacificus_EcoDAAT <- filter(Calanus_pacificus, DATA_SOURCE=="EcoDAAT")

#Check to see if right stages are in the EcoDAAT data

Calanus_pacificus_EcoDAAT_bySPECIMEN_FORM <- group_by(Calanus_pacificus_EcoDAAT, SPECIMEN_FORM, MESH, GEAR_NAME)

Calanus_pacificus_EcoDAAT_FormSummary <- summarise(Calanus_pacificus_EcoDAAT_bySPECIMEN_FORM,n())

`summarise()` has grouped output by 'SPECIMEN_FORM', 'MESH'. You can override using
the `.groups` argument.

#Stages and gear are correct for EcoDAAT data


#Now filter the EMA data to match the EcoDAAT data. EMA tends to double count variables from both nets, so eliminate this

#Check to see if what stages are where with EMA data

Calanus_pacificus_EMA_byGEAR_NAME <- group_by(Calanus_pacificus_EMA, MESH, GEAR_NAME)

Calanus_pacificus_EMA_GearSummary <- summarise(Calanus_pacificus_EMA_byGEAR_NAME, n())

`summarise()` has grouped output by 'MESH'. You can override using the `.groups`
argument.

# Need to filter for the correct stages for avoid double counts, just remove one Juday sample

Calanus_pacificus_EMA <- filter(Calanus_pacificus_EMA, GEAR_NAME!="Juday")



#Combine into final, Calanus_pacificus data set

Calanus_pacificus <- rbind(Calanus_pacificus_EMA, Calanus_pacificus_EcoDAAT)

#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Calanus_pacificus)

Caridea

Caridea <- filter(NBS_Zoop_Process, TAXA_COARSE == "Caridea")

#Caridea estimate from larger nets only

Caridea <- filter(Caridea, GEAR_NAME=="60BON")

#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Caridea)

Centropages abdominalis

Centropages <- filter(NBS_Zoop_Process, TAXA_COARSE=="Centropages abdominalis")


#Separate EMA data as they were sorted under different protocols

Centropages_EMA <- filter(Centropages, DATA_SOURCE=="EMA")
Centropages_EcoDAAT <- filter(Centropages, DATA_SOURCE=="EcoDAAT")

#Check to see if right stages are in the EcoDAAT data

Centropages_EcoDAAT_bySPECIMEN_FORM <- group_by(Centropages_EcoDAAT, SPECIMEN_FORM, MESH, GEAR_NAME)

Centropages_EcoDAAT_FormSummary <- summarise(Centropages_EcoDAAT_bySPECIMEN_FORM,n())

`summarise()` has grouped output by 'SPECIMEN_FORM', 'MESH'. You can override using
the `.groups` argument.

#Filter for correct GEAR_NAME and MESH from EcoDAAT

Centropages_EcoDAAT <- filter(Centropages_EcoDAAT, SPECIMEN_FORM!="G")


#Now filter the EMA data to match the EcoDAAT data. EMA tends to double count variables from both nets, so eliminate this

#Check to see if what stages are where with EMA data

Centropages_EMA_byGEAR_NAME <- group_by(Centropages_EMA, MESH, GEAR_NAME)

Centropages_EMA_GearSummary <- summarise(Centropages_EMA_byGEAR_NAME, n())

`summarise()` has grouped output by 'MESH'. You can override using the `.groups`
argument.

#For consistency, select the smaller gear only

Centropages_EMA <- filter(Centropages_EMA, GEAR_NAME!="60BON")


#Recombined data

Centropages <- rbind(Centropages_EcoDAAT, Centropages_EMA)



#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Centropages)

Chaetognatha

Chaetognatha <- filter(NBS_Zoop_Process, TAXA_COARSE=="Chaetognatha")

#Filter for Chaetognatha from the 60BON nets only

Chaetognatha <- filter(Chaetognatha, GEAR_NAME=="60BON")

#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Chaetognatha)

Cirripedia

Cirripedia <- filter(NBS_Zoop_Process, TAXA_COARSE == "Cirripedia")

#Can filter for both gears and then add a taxa coarse of Cirripedia_large and Cirripedia_small

Cirripedia_large <- filter(Cirripedia, GEAR_NAME=="60BON")

#Recode coarse taxa

Cirripedia_large$TAXA_COARSE[Cirripedia_large$TAXA_COARSE=="Cirripedia"] <- "Cirripedia_large"


Cirripedia_small <- filter(Cirripedia, GEAR_NAME!="60BON")

#Recode coarse taxa

Cirripedia_small$TAXA_COARSE[Cirripedia_small$TAXA_COARSE=="Cirripedia"] <- "Cirripedia_small"

#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Cirripedia_large, Cirripedia_small)

Cladocera

Cladocera <- filter(NBS_Zoop_Process, TAXA_COARSE=="Cladocera")

#Cladocera fromt he small net only

#Filter for correct gear

Cladocera <- filter(Cladocera, GEAR_NAME!= "60BON")


#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Cladocera)

Clione limacina

Clione <- filter(NBS_Zoop_Process, TAXA_COARSE=="Clione limacina")

#Estimate from the larger net only

Clione <- filter(Clione, GEAR_NAME=="60BON")


#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Clione)

Cnidaria

Cnidaria <- filter(NBS_Zoop_Process, TAXA_COARSE == "Cnidaria")

#Can filter for both gears and then add a taxa coarse of Cnidaria_large and Cnidaria_small

Cnidaria_large <- filter(Cnidaria, GEAR_NAME=="60BON")

#Recode coarse taxa

Cnidaria_large$TAXA_COARSE[Cnidaria_large$TAXA_COARSE=="Cnidaria"] <- "Cnidaria_large"


Cnidaria_small <- filter(Cnidaria, GEAR_NAME!="60BON")

#Recode coarse taxa

Cnidaria_small$TAXA_COARSE[Cnidaria_small$TAXA_COARSE=="Cnidaria"] <- "Cnidaria_small"


#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Cnidaria_large, Cnidaria_small)

Small and large copepods that do not belong to major taxonomic group

Copepod_small <- filter(NBS_Zoop_Process, TAXA_COARSE == "Copepod_small")

#Filter for the smaller mesh gears only

Copepod_small <- filter(Copepod_small, GEAR_NAME!="60BON")

#Now build the large dataset

Copepod_large <- filter(NBS_Zoop_Process, TAXA_COARSE == "Copepod_large")

#Filter for the smaller mesh gears only

Copepod_large <- filter(Copepod_large, GEAR_NAME=="60BON")

#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Copepod_large, Copepod_small)

Ctenophora

Ctenophora <- filter(NBS_Zoop_Process, TAXA_COARSE=="Ctenophora")

#Filter for the large net only

Ctenophora <- filter(Ctenophora, GEAR_NAME=="60BON")

#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Ctenophora)

Cumacea

Cumacea <- filter(NBS_Zoop_Process, TAXA_COARSE=="Cumacea")

#Filter for the large net only

Cumacea <- filter(Cumacea, GEAR_NAME=="60BON")

#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Cumacea)

Decapoda

Decapoda <- filter(NBS_Zoop_Process, TAXA_COARSE=="Decapoda")

#Very few measurements of unidentfied decapods. We can ignore

Echinodermata

Echinodermata <- filter(NBS_Zoop_Process, TAXA_COARSE=="Echinodermata")

#Echinodermata are tiny, filter from small nets only

Echinodermata <- filter(Echinodermata, GEAR_NAME!="60BON")

#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Echinodermata)

Epilabidocera longipedata

Epilabidocera <- filter(NBS_Zoop_Process, TAXA_COARSE=="Epilabidocera longipedata")


#Separate EMA data as they were sorted under different protocols

Epilabidocera_EMA <- filter(Epilabidocera, DATA_SOURCE=="EMA")
Epilabidocera_EcoDAAT <- filter(Epilabidocera, DATA_SOURCE=="EcoDAAT")

#Check to see if right stages are in the EcoDAAT data

Epilabidocera_EcoDAAT_bySPECIMEN_FORM <- group_by(Epilabidocera_EcoDAAT, SPECIMEN_FORM, MESH, GEAR_NAME)

Epilabidocera_EcoDAAT_FormSummary <- summarise(Epilabidocera_EcoDAAT_bySPECIMEN_FORM,n())

`summarise()` has grouped output by 'SPECIMEN_FORM', 'MESH'. You can override using
the `.groups` argument.

#Things are correct for the EcoDAAT data, not look at the EMA data


#Now filter the EMA data to match the EcoDAAT data. EMA tends to double count variables from both nets, so eliminate this

#Check to see if what stages are where with EMA data

Epilabidocera_EMA_byGEAR_NAME <- group_by(Epilabidocera_EMA, MESH, GEAR_NAME)

Epilabidocera_EMA_GearSummary <- summarise(Epilabidocera_EMA_byGEAR_NAME, n())

`summarise()` has grouped output by 'MESH'. You can override using the `.groups`
argument.

#No issues with mismatched mesh and gear sizes. Need to filter for the correct stages for avoid double counts

Epilabidocera_EMA_60BON <- filter(Epilabidocera_EMA, GEAR_NAME=="60BON")

Epilabidocera_EMA_60BON_333 <- filter(Epilabidocera_EMA_60BON, MESH==333)

Epilabidocera_EMA_60BON_333 <- filter(Epilabidocera_EMA_60BON_333, STAGE_NAME=="ADULT"|STAGE_NAME=="C - 5 (COPEPODITE V)"|STAGE_NAME=="C - 4 (COPEPODITE IV)"|STAGE_NAME=="C - 3 (COPEPODITE III)")

Epilabidocera_EMA_60BON_505 <- filter(Epilabidocera_EMA_60BON, MESH==505)

Epilabidocera_EMA_60BON_505 <- filter(Epilabidocera_EMA_60BON_505, STAGE_NAME=="ADULT"|STAGE_NAME=="C - 5 (COPEPODITE V)"|STAGE_NAME=="C - 4 (COPEPODITE IV)")

Epilabidocera_EMA_20BON <- filter(Epilabidocera_EMA, GEAR_NAME=="20BON")

Epilabidocera_EMA_20BON_153 <- filter(Epilabidocera_EMA_20BON, MESH==153)

Epilabidocera_EMA_20BON_153 <- filter(Epilabidocera_EMA_20BON_153, STAGE_NAME=="C - 2 (COPEPODITE II)"|STAGE_NAME=="C - 1 (COPEPODITE I)")

#The other gears are correct, so rebuild dataset

Epilabidocera_EMA_Final <- rbind(Epilabidocera_EMA_60BON_333, Epilabidocera_EMA_60BON_505, Epilabidocera_EMA_20BON_153)

ungroup(Epilabidocera_EMA_Final)

#Remove some files

rm(Epilabidocera_EMA_byGEAR_NAME, Epilabidocera_EMA_20BON, Epilabidocera_EMA_20BON_153, Epilabidocera_EMA_60BON, Epilabidocera_EMA_60BON_333, Epilabidocera_EMA_60BON_505)

#Combine into final, Epilabidocera data set

Epilabidocera <- rbind(Epilabidocera_EMA_Final, Epilabidocera_EcoDAAT)

#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Epilabidocera)

Eucalanus bungii

Eucalanus <- filter(NBS_Zoop_Process, TAXA_COARSE=="Eucalanus bungii")


#Separate EMA data as they were sorted under different protocols

Eucalanus_EMA <- filter(Eucalanus, DATA_SOURCE=="EMA")
Eucalanus_EcoDAAT <- filter(Eucalanus, DATA_SOURCE=="EcoDAAT")

#Check to see if right stages are in the EcoDAAT data

Eucalanus_EcoDAAT_bySPECIMEN_FORM <- group_by(Eucalanus_EcoDAAT, SPECIMEN_FORM, MESH, GEAR_NAME)

Eucalanus_EcoDAAT_FormSummary <- summarise(Eucalanus_EcoDAAT_bySPECIMEN_FORM,n())

`summarise()` has grouped output by 'SPECIMEN_FORM', 'MESH'. You can override using
the `.groups` argument.

#Do some filtering to get the correct stages from the correct gear for EcoDAAT data

Eucalanus_EcoDAAT_A <- filter(Eucalanus_EcoDAAT, SPECIMEN_FORM=="A")
Eucalanus_EcoDAAT_A <- filter(Eucalanus_EcoDAAT_A, MESH!=153)

Eucalanus_EcoDAAT_B <- filter(Eucalanus_EcoDAAT, SPECIMEN_FORM=="B")
Eucalanus_EcoDAAT_B <- filter(Eucalanus_EcoDAAT_B, MESH!=153)

Eucalanus_EcoDAAT_C <- filter(Eucalanus_EcoDAAT, SPECIMEN_FORM=="C")
Eucalanus_EcoDAAT_C <- filter(Eucalanus_EcoDAAT_C, MESH==153)

Eucalanus_EcoDAAT_F <- filter(Eucalanus_EcoDAAT, SPECIMEN_FORM=="F")


Eucalanus_EcoDAAT_G <- filter(Eucalanus_EcoDAAT, SPECIMEN_FORM=="G")

Eucalanus_EcoDAAT_H <- filter(Eucalanus_EcoDAAT, SPECIMEN_FORM=="H")

Eucalanus_EcoDAAT_K <- filter(Eucalanus_EcoDAAT, SPECIMEN_FORM=="K")

Eucalanus_EcoDAAT_L <- filter(Eucalanus_EcoDAAT, SPECIMEN_FORM=="L")

#The other gears are correct, so rebuild dataset

Eucalanus_EcoDAAT_Final <- rbind(Eucalanus_EcoDAAT_A, Eucalanus_EcoDAAT_B, Eucalanus_EcoDAAT_C, Eucalanus_EcoDAAT_F,  Eucalanus_EcoDAAT_G, Eucalanus_EcoDAAT_H, Eucalanus_EcoDAAT_K, Eucalanus_EcoDAAT_L)

ungroup(Eucalanus_EcoDAAT_Final)

#Remove some files

rm(Eucalanus_EcoDAAT_bySPECIMEN_FORM, Eucalanus_EcoDAAT_A, Eucalanus_EcoDAAT_B, Eucalanus_EcoDAAT_C, Eucalanus_EcoDAAT_F, Eucalanus_EcoDAAT_G, Eucalanus_EcoDAAT_H, Eucalanus_EcoDAAT_K, Eucalanus_EcoDAAT_L)



#Now filter the EMA data to match the EcoDAAT data. EMA tends to double count variables from both nets, so eliminate this

#Check to see if what stages are where with EMA data

Eucalanus_EMA_byGEAR_NAME <- group_by(Eucalanus_EMA, MESH, GEAR_NAME)

Eucalanus_EMA_GearSummary <- summarise(Eucalanus_EMA_byGEAR_NAME, n())

`summarise()` has grouped output by 'MESH'. You can override using the `.groups`
argument.

#No issues with mismatched mesh and gear sizes. Need to filter for the correct stages for avoid double counts

Eucalanus_EMA_60BON <- filter(Eucalanus_EMA, GEAR_NAME=="60BON")

Eucalanus_EMA_60BON_333 <- filter(Eucalanus_EMA_60BON, MESH==333)

Eucalanus_EMA_60BON_333 <- filter(Eucalanus_EMA_60BON_333, STAGE_NAME=="ADULT"|STAGE_NAME=="C - 5 (COPEPODITE V)"|STAGE_NAME=="C - 4 (COPEPODITE IV)"|STAGE_NAME=="C - 3 (COPEPODITE III)")

Eucalanus_EMA_60BON_505 <- filter(Eucalanus_EMA_60BON, MESH==505)

Eucalanus_EMA_60BON_505 <- filter(Eucalanus_EMA_60BON_505, STAGE_NAME=="ADULT"|STAGE_NAME=="C - 5 (COPEPODITE V)"|STAGE_NAME=="C - 4 (COPEPODITE IV)"|STAGE_NAME=="C - 3 (COPEPODITE III)")

Eucalanus_EMA_20BON <- filter(Eucalanus_EMA, GEAR_NAME=="20BON")

Eucalanus_EMA_20BON_153 <- filter(Eucalanus_EMA_20BON, MESH==153)

Eucalanus_EMA_20BON_153 <- filter(Eucalanus_EMA_20BON_153, STAGE_NAME=="C - 2 (COPEPODITE II)"|STAGE_NAME=="C - 1 (COPEPODITE I)")

#The other gears are correct, so rebuild dataset

Eucalanus_EMA_Final <- rbind(Eucalanus_EMA_60BON_333, Eucalanus_EMA_60BON_505, Eucalanus_EMA_20BON_153)

ungroup(Eucalanus_EMA_Final)

#Remove some files

rm(Eucalanus_EMA_byGEAR_NAME, Eucalanus_EMA_20BON, Eucalanus_EMA_20BON_153, Eucalanus_EMA_60BON, Eucalanus_EMA_60BON_333, Eucalanus_EMA_60BON_505)

#Combine into final, Eucalanus data set

Eucalanus <- rbind(Eucalanus_EMA_Final, Eucalanus_EcoDAAT_Final)


#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Eucalanus)

Euphausiacea pacifica

E_pacifica <- filter(NBS_Zoop_Process, TAXA_COARSE=="Euphausia pacifica")

#Filter for large net only and stages are adult and juvenile

E_pacifica <- filter(E_pacifica, GEAR_NAME=="60BON")

#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, E_pacifica)

Euphausiacea

Euphausiacea <- filter(NBS_Zoop_Process, TAXA_COARSE=="Euphausiacea")

#First separate out the adults belonging to Tessarbranchion oculatum

    
Tessarabrachion_oculatum <- filter (Euphausiacea, TAXON_NAME=="Tessarabrachion oculatum")


#Now filter the Euphausiacea for the correct stages and nets

Euphausiacea <- filter(Euphausiacea, TAXON_NAME!="Tessarabrachion oculatum")

#Eliminate adult and juvenile stages, those should be identified to species

Euphausiacea <- filter(Euphausiacea, STAGE_NAME!= "A + J (ADULT/JUVENILE)")

Euphausiacea <- filter(Euphausiacea, STAGE_NAME!= "JUVENILE")

#Get rid of the NOT DETERMINED

Euphausiacea <- filter(Euphausiacea, STAGE_NAME!="NOT DETERMINED")

#Get rid of the EGG

Euphausiacea <- filter(Euphausiacea, STAGE_NAME!="EGG")


#Now create the furcilia dataset

Euphausiacea_furcilia <- filter(Euphausiacea, STAGE_NAME=="FURCILIA")

Euphausiacea_furcilia <- filter(Euphausiacea, GEAR_NAME=="60BON")


#Now create the calytopis dataset

Euphausiacea_calyptopis <- filter(Euphausiacea, STAGE_NAME=="CALYPTOPIS (STAGE NOT DETERMINED)"|STAGE_NAME=="CALYPTOPIS 1"|STAGE_NAME=="CALYPTOPIS 2"|STAGE_NAME=="CALYPTOPIS 3")


#Now create the nauplius dataset

Euphausiacea_nauplius <- filter(Euphausiacea, STAGE_NAME=="NAUPLIUS")

#Filter for small nets only

Euphausiacea_nauplius <- filter(Euphausiacea_nauplius, GEAR_NAME!="60BON")


#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Euphausiacea_furcilia, Euphausiacea_calyptopis, Euphausiacea_nauplius)

Eurytemora spp.

Eurytemora <- filter(NBS_Zoop_Process, TAXA_COARSE=="Eurytemora spp.")

#Filter from the small nets only

Eurytemora <- filter(Eurytemora, GEAR_NAME!="60BON")


#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Eurytemora)

Gastropoda

Gastropoda <- filter(NBS_Zoop_Process, TAXA_COARSE=="Gastropoda")

#Unidentified gastropods, can remove from final dataset

Limacina helicina

Limacina <- filter(NBS_Zoop_Process, TAXA_COARSE=="Limacina helicina")

#Can split into estiamtes from large and small nets


Limacina_large <- filter(Limacina, GEAR_NAME=="60BON")

#Rename the coarse taxa

Limacina_large$TAXA_COARSE[Limacina_large$TAXA_COARSE=="Limacina helicina"] <- "Limacina_large"

#Now do the small nets

Limacina_small <- filter(Limacina, GEAR_NAME!="60BON")

#Rename the coarse taxa

Limacina_small$TAXA_COARSE[Limacina_small$TAXA_COARSE=="Limacina helicina"] <- "Limacina_small"


#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Limacina_large, Limacina_small)

Metridia longa

Metridia_longa <- filter(NBS_Zoop_Process, TAXA_COARSE=="Metridia longa")

#Adults, C5 only so all is good, can add to full data set

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Metridia_longa)

Metridia okhotensis

Metridia_okhotensis <- filter(NBS_Zoop_Process, TAXA_COARSE=="Metridia okhotensis")


#Adults, C4, and C5 only so all is good, can add to full data set

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Metridia_okhotensis)

Metridia pacifica

Metridia_pacifica <- filter(NBS_Zoop_Process, TAXA_COARSE=="Metridia pacifica")


#Separate EMA data as they were sorted under different protocols

Metridia_pacifica_EMA <- filter(Metridia_pacifica, DATA_SOURCE=="EMA")
Metridia_pacifica_EcoDAAT <- filter(Metridia_pacifica, DATA_SOURCE=="EcoDAAT")

#Check to see if right stages are in the EcoDAAT data

Metridia_pacifica_EcoDAAT_bySPECIMEN_FORM <- group_by(Metridia_pacifica_EcoDAAT, SPECIMEN_FORM, MESH, GEAR_NAME)

Metridia_pacifica_EcoDAAT_FormSummary <- summarise(Metridia_pacifica_EcoDAAT_bySPECIMEN_FORM,n())

`summarise()` has grouped output by 'SPECIMEN_FORM', 'MESH'. You can override using
the `.groups` argument.

#Do some filtering to get the correct stages from the correct gear for EcoDAAT data

Metridia_pacifica_EcoDAAT_B <- filter(Metridia_pacifica_EcoDAAT, SPECIMEN_FORM=="B")
Metridia_pacifica_EcoDAAT_B <- filter(Metridia_pacifica_EcoDAAT_B, MESH!=153)

Metridia_pacifica_EcoDAAT_C <- filter(Metridia_pacifica_EcoDAAT, SPECIMEN_FORM=="C")

Metridia_pacifica_EcoDAAT_G <- filter(Metridia_pacifica_EcoDAAT, SPECIMEN_FORM=="G")


Metridia_pacifica_EcoDAAT_H <- filter(Metridia_pacifica_EcoDAAT, SPECIMEN_FORM=="H")

#Remove C3 stage

Metridia_pacifica_EcoDAAT_H <- filter(Metridia_pacifica_EcoDAAT_H, STAGE_NAME!="C - 3 (COPEPODITE III)")


Metridia_pacifica_EcoDAAT_K <- filter(Metridia_pacifica_EcoDAAT, SPECIMEN_FORM=="K")

Metridia_pacifica_EcoDAAT_L <- filter(Metridia_pacifica_EcoDAAT, SPECIMEN_FORM=="L")

#The other gears are correct, so rebuild dataset

Metridia_pacifica_EcoDAAT_Final <- rbind(Metridia_pacifica_EcoDAAT_B, Metridia_pacifica_EcoDAAT_C, Metridia_pacifica_EcoDAAT_G, Metridia_pacifica_EcoDAAT_H, Metridia_pacifica_EcoDAAT_K, Metridia_pacifica_EcoDAAT_L)

ungroup(Metridia_pacifica_EcoDAAT_Final)

#Remove some files

rm(Metridia_pacifica_EcoDAAT_bySPECIMEN_FORM, Metridia_pacifica_EcoDAAT_B, Metridia_pacifica_EcoDAAT_C, Metridia_pacifica_EcoDAAT_G, Metridia_pacifica_EcoDAAT_H, Metridia_pacifica_EcoDAAT_K, Metridia_pacifica_EcoDAAT_L)

#Now filter the EMA data to match the EcoDAAT data. EMA tends to double count variables from both nets, so eliminate this

#Check to see if what stages are where with EMA data

Metridia_pacifica_EMA_byGEAR_NAME <- group_by(Metridia_pacifica_EMA, MESH, GEAR_NAME)

Metridia_pacifica_EMA_GearSummary <- summarise(Metridia_pacifica_EMA_byGEAR_NAME, n())

`summarise()` has grouped output by 'MESH'. You can override using the `.groups`
argument.

#No issues with mismatched mesh and gear sizes. Need to filter for the correct stages for avoid double counts

Metridia_pacifica_EMA_60BON <- filter(Metridia_pacifica_EMA, GEAR_NAME=="60BON")

Metridia_pacifica_EMA_60BON_333 <- filter(Metridia_pacifica_EMA_60BON, MESH==333)

Metridia_pacifica_EMA_60BON_333 <- filter(Metridia_pacifica_EMA_60BON_333, STAGE_NAME=="ADULT"|STAGE_NAME=="C - 5 (COPEPODITE V)"|STAGE_NAME=="C - 4 (COPEPODITE IV)")

Metridia_pacifica_EMA_60BON_505 <- filter(Metridia_pacifica_EMA_60BON, MESH==505)

Metridia_pacifica_EMA_60BON_505 <- filter(Metridia_pacifica_EMA_60BON_505, STAGE_NAME=="ADULT"|STAGE_NAME=="C - 5 (COPEPODITE V)"|STAGE_NAME=="C - 4 (COPEPODITE IV)")



Metridia_pacifica_EMA_smallnets <- filter(Metridia_pacifica_EMA, GEAR_NAME!="60BON")

Metridia_pacifica_EMA_smallnets <- filter(Metridia_pacifica_EMA_smallnets, STAGE_NAME=="C - 1 (COPEPODITE I)"|STAGE_NAME=="C - 2 (COPEPODITE II)"|STAGE_NAME=="C - 3 (COPEPODITE III)")

#Rename Metridia pacific of early stages as Metridia spp.

Metridia_pacifica_EMA_smallnets$TAXA_COARSE[Metridia_pacifica_EMA_smallnets$TAXA_COARSE=="Metridia pacifica"] <- "Metridia spp."

#The other gears are correct, so rebuild dataset

Metridia_pacifica_EMA_Final <- rbind(Metridia_pacifica_EMA_60BON_333, Metridia_pacifica_EMA_60BON_505, Metridia_pacifica_EMA_smallnets)

ungroup(Metridia_pacifica_EMA_Final)

#Remove some files

rm(Metridia_pacifica_EMA_byGEAR_NAME, Metridia_pacifica_EMA_smallnets, Metridia_pacifica_EMA_60BON, Metridia_pacifica_EMA_60BON_333, Metridia_pacifica_EMA_60BON_505)

#Combine into final, Metridia_pacifica data set

Metridia_pacifica <- rbind(Metridia_pacifica_EMA_Final, Metridia_pacifica_EcoDAAT_Final)

#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Metridia_pacifica)

Metridia spp.

Metridia_spp <- filter(NBS_Zoop_Process, TAXA_COARSE=="Metridia spp.")

#Filter for the small nets only

Metridia_spp <- filter(Metridia_spp, GEAR_NAME!="60BON")

#Now filter out the stages that are accurate for the small nets, anything less than stage C-3

Metridia_spp <- filter(Metridia_spp, STAGE_NAME!= "C-1 TO C-5")
Metridia_spp <- filter(Metridia_spp, STAGE_NAME!= "C3-4")
Metridia_spp <- filter(Metridia_spp, STAGE_NAME!= "C3-5")
Metridia_spp <- filter(Metridia_spp, STAGE_NAME!= "C - 4 (COPEPODITE IV)")


#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Metridia_spp)

Mysids

Mysidae <- filter(NBS_Zoop_Process, TAXA_COARSE=="Mysidae")

#Filter for 60BON nets only

Mysidae <- filter(Mysidae, GEAR_NAME=="60BON")


#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Mysidae)

Neocalanus cristatus

Cristatus <- filter(NBS_Zoop_Process, TAXA_COARSE=="Neocalanus cristatus")


#Separate EMA data as they were sorted under different protocols

Cristatus_EMA <- filter(Cristatus, DATA_SOURCE=="EMA")
Cristatus_EcoDAAT <- filter(Cristatus, DATA_SOURCE=="EcoDAAT")

#Check to see if right stages are in the EcoDAAT data

Cristatus_EcoDAAT_bySPECIMEN_FORM <- group_by(Cristatus_EcoDAAT, SPECIMEN_FORM, MESH, GEAR_NAME)

Cristatus_EcoDAAT_FormSummary <- summarise(Cristatus_EcoDAAT_bySPECIMEN_FORM,n())

`summarise()` has grouped output by 'SPECIMEN_FORM', 'MESH'. You can override using
the `.groups` argument.

#Do some filtering to get the correct stages from the correct gear for EcoDAAT data

Cristatus_EcoDAAT_A <- filter(Cristatus_EcoDAAT, SPECIMEN_FORM=="A")
Cristatus_EcoDAAT_A <- filter(Cristatus_EcoDAAT_A, MESH!=153)

Cristatus_EcoDAAT_B <- filter(Cristatus_EcoDAAT, SPECIMEN_FORM=="B")
Cristatus_EcoDAAT_B <- filter(Cristatus_EcoDAAT_B, MESH!=153)

Cristatus_EcoDAAT_C <- filter(Cristatus_EcoDAAT, SPECIMEN_FORM=="C")
Cristatus_EcoDAAT_C <- filter(Cristatus_EcoDAAT_C, MESH==153)
Cristatus_EcoDAAT_C <- filter(Cristatus_EcoDAAT_C, GEAR_NAME=="20BON")

Cristatus_EcoDAAT_F <- filter(Cristatus_EcoDAAT, SPECIMEN_FORM=="F")

Cristatus_EcoDAAT_G <- filter(Cristatus_EcoDAAT, SPECIMEN_FORM=="G")

Cristatus_EcoDAAT_H <- filter(Cristatus_EcoDAAT, SPECIMEN_FORM=="H")

Cristatus_EcoDAAT_K <- filter(Cristatus_EcoDAAT, SPECIMEN_FORM=="K")

Cristatus_EcoDAAT_L <- filter(Cristatus_EcoDAAT, SPECIMEN_FORM=="L")

#The other gears are correct, so rebuild dataset

Cristatus_EcoDAAT_Final <- rbind(Cristatus_EcoDAAT_A, Cristatus_EcoDAAT_B, Cristatus_EcoDAAT_C, Cristatus_EcoDAAT_F, Cristatus_EcoDAAT_G, Cristatus_EcoDAAT_H, Cristatus_EcoDAAT_K, Cristatus_EcoDAAT_L)

ungroup(Cristatus_EcoDAAT_Final)

#Remove some files

rm(Cristatus_EcoDAAT_bySPECIMEN_FORM, Cristatus_EcoDAAT_A, Cristatus_EcoDAAT_B, Cristatus_EcoDAAT_C, Cristatus_EcoDAAT_F, Cristatus_EcoDAAT_G, Cristatus_EcoDAAT_H, Cristatus_EcoDAAT_K, Cristatus_EcoDAAT_L)

#Now filter the EMA data to match the EcoDAAT data. EMA tends to double count variables from both nets, so eliminate this

#Check to see if what stages are where with EMA data

Cristatus_EMA_byGEAR_NAME <- group_by(Cristatus_EMA, MESH, GEAR_NAME)

Cristatus_EMA_GearSummary <- summarise(Cristatus_EMA_byGEAR_NAME, n())

`summarise()` has grouped output by 'MESH'. You can override using the `.groups`
argument.

#No issues with mismatched mesh and gear sizes. Need to filter for the correct stages for avoid double counts

Cristatus_EMA_Final <-  filter(Cristatus_EMA, STAGE_NAME=="ADULT"|STAGE_NAME=="C - 5 (COPEPODITE V)"|STAGE_NAME=="C - 4 (COPEPODITE IV)"|STAGE_NAME=="C - 3 (COPEPODITE III)")


ungroup(Cristatus_EMA_Final)

#Now combine EMA and EcoDAAT data together

Cristatus_Final <- rbind(Cristatus_EMA_Final, Cristatus_EcoDAAT_Final)


#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Cristatus_Final)

Neocalanus spp.

Neocalanus <- filter(NBS_Zoop_Process, TAXA_COARSE=="Neocalanus spp.")


#Separate EMA data as they were sorted under different protocols

Neocalanus_EMA <- filter(Neocalanus, DATA_SOURCE=="EMA")
Neocalanus_EcoDAAT <- filter(Neocalanus, DATA_SOURCE=="EcoDAAT")

#Check to see if right stages are in the EcoDAAT data

Neocalanus_EcoDAAT_bySPECIMEN_FORM <- group_by(Neocalanus_EcoDAAT, SPECIMEN_FORM, MESH, GEAR_NAME)

Neocalanus_EcoDAAT_FormSummary <- summarise(Neocalanus_EcoDAAT_bySPECIMEN_FORM,n())

`summarise()` has grouped output by 'SPECIMEN_FORM', 'MESH'. You can override using
the `.groups` argument.

#Do some filtering to get the correct stages from the correct gear for EcoDAAT data

Neocalanus_EcoDAAT_B <- filter(Neocalanus_EcoDAAT, SPECIMEN_FORM=="B")
Neocalanus_EcoDAAT_B <- filter(Neocalanus_EcoDAAT_B, MESH!=153)

Neocalanus_EcoDAAT_C <- filter(Neocalanus_EcoDAAT, SPECIMEN_FORM=="C")
Neocalanus_EcoDAAT_C <- filter(Neocalanus_EcoDAAT_C, MESH==153)
Neocalanus_EcoDAAT_C <- filter(Neocalanus_EcoDAAT_C, GEAR_NAME=="20BON")

Neocalanus_EcoDAAT_G <- filter(Neocalanus_EcoDAAT, SPECIMEN_FORM=="G")

Neocalanus_EcoDAAT_H <- filter(Neocalanus_EcoDAAT, SPECIMEN_FORM=="H")

Neocalanus_EcoDAAT_K <- filter(Neocalanus_EcoDAAT, SPECIMEN_FORM=="K")

Neocalanus_EcoDAAT_L <- filter(Neocalanus_EcoDAAT, SPECIMEN_FORM=="L")

#The other gears are correct, so rebuild dataset

Neocalanus_EcoDAAT_Final <- rbind(Neocalanus_EcoDAAT_B, Neocalanus_EcoDAAT_C, Neocalanus_EcoDAAT_G, Neocalanus_EcoDAAT_H, Neocalanus_EcoDAAT_K, Neocalanus_EcoDAAT_L)

ungroup(Neocalanus_EcoDAAT_Final)

#Remove some files

rm(Neocalanus_EcoDAAT_bySPECIMEN_FORM, Neocalanus_EcoDAAT_B, Neocalanus_EcoDAAT_C, Neocalanus_EcoDAAT_G, Neocalanus_EcoDAAT_H, Neocalanus_EcoDAAT_K, Neocalanus_EcoDAAT_L)

#Now filter the EMA data to match the EcoDAAT data. EMA tends to double count variables from both nets, so eliminate this

#Check to see if what stages are where with EMA data

Neocalanus_EMA_byGEAR_NAME <- group_by(Neocalanus_EMA, MESH, GEAR_NAME)

Neocalanus_EMA_GearSummary <- summarise(Neocalanus_EMA_byGEAR_NAME, n())

`summarise()` has grouped output by 'MESH'. You can override using the `.groups`
argument.

#No issues with mismatched mesh and gear sizes. Need to filter for the correct stages for avoid double counts

Neocalanus_EMA_Final <-  filter(Neocalanus_EMA, STAGE_NAME=="ADULT"|STAGE_NAME=="C - 5 (COPEPODITE V)"|STAGE_NAME=="C - 4 (COPEPODITE IV)"|STAGE_NAME=="C - 3 (COPEPODITE III)")


ungroup(Neocalanus_EMA_Final)

#NOw combine EMA and EcoDAAT data together

Neocalanus_Final <- rbind(Neocalanus_EMA_Final, Neocalanus_EcoDAAT_Final)

#Add to final dataset


NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Neocalanus_Final)

Oithona spp.

Oithona <- filter(NBS_Zoop_Process, TAXA_COARSE=="Oithona spp.")

#Filter for small nets only

Oithona <- filter(Oithona, GEAR_NAME!="60BON")


#Add to final dataset


NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Oithona)

Ostracoda

Ostracoda <- filter(NBS_Zoop_Process, TAXA_COARSE=="Ostracoda")

Polychaeta

Polychaeta <- filter(NBS_Zoop_Process, TAXA_COARSE=="Polychaeta")

#Split into small and large estimates from the correct nets and meshes

Polychaeta_large <- filter(Polychaeta, GEAR_NAME=="60BON")


#Rename Polychaeta large

Polychaeta_large$TAXA_COARSE[Polychaeta_large$TAXA_COARSE=="Polychaeta"] <- "Polychaeta_large"


#Now do the small nets

Polychaeta_small <- filter(Polychaeta, GEAR_NAME!="60BON")

#Rename Polychaeta small

Polychaeta_small$TAXA_COARSE[Polychaeta_small$TAXA_COARSE=="Polychaeta"] <- "Polychaeta_small"


#Add to final dataset


NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Polychaeta_large, Polychaeta_small)

Pseudocalanus

Pseudocalanus <- filter(NBS_Zoop_Process, TAXA_COARSE=="Pseudocalanus spp.")

#Filter for the small nets only

Pseudocalanus <- filter(Pseudocalanus, GEAR_NAME!="60BON")


#Add to final dataset


NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Pseudocalanus)

Thaliacea

Thaliacea <- filter(NBS_Zoop_Process, TAXA_COARSE=="Thaliacea")

Themisto abyssorum

Themisto_abyssorum <- filter(NBS_Zoop_Process, TAXA_COARSE=="Themisto abyssorum")

Themisto libellula

Themisto_libellula <- filter(NBS_Zoop_Process, TAXA_COARSE=="Themisto libellula")

#Filter for the 60BON nets only

Themisto_libellula <- filter(Themisto_libellula, GEAR_NAME=="60BON")

#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Themisto_libellula)

Themisto pacifica

Themisto_pacifica <- filter(NBS_Zoop_Process, TAXA_COARSE=="Themisto pacifica")

#Filter for the 60BON nets only

Themisto_pacifica <- filter(Themisto_pacifica, GEAR_NAME=="60BON")

#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Themisto_pacifica)

Themisto spp.

Themisto <- filter(NBS_Zoop_Process, TAXA_COARSE=="Themisto spp.")

#Filter for the 60BON nets only

Themisto<- filter(Themisto, GEAR_NAME=="60BON")

#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Themisto)

Thysanoessa species

Thysanoessa <- filter(NBS_Zoop_Process, TAXA_COARSE=="Thysanoessa inermis"|TAXA_COARSE=="Thysanoessa inspinata"|TAXA_COARSE=="Thysanoessa longipes"|TAXA_COARSE=="Thysanoessa raschii"|TAXA_COARSE=="Thysanoessa spinifera")

#Select for 60BON only

Thysanoessa <- filter(Thysanoessa, GEAR_NAME=="60BON")

#Now the correct stages

Thysanoessa <- filter(Thysanoessa, STAGE_NAME=="A + J (ADULT/JUVENILE)"|STAGE_NAME=="JUVENILE"|STAGE_NAME=="ADULT")

#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Thysanoessa)

Tortanus discaudatus

Tortanus <- filter(NBS_Zoop_Process, TAXA_COARSE=="Tortanus discaudatus")

#Separate EMA data as they were sorted under different protocols

Tortanus_EMA <- filter(Tortanus, DATA_SOURCE=="EMA")
Tortanus_EcoDAAT <- filter(Tortanus, DATA_SOURCE=="EcoDAAT")

#Check to see if right stages are in the EcoDAAT data

Tortanus_EcoDAAT_bySPECIMEN_FORM <- group_by(Tortanus_EcoDAAT, SPECIMEN_FORM, MESH, GEAR_NAME)

Tortanus_EcoDAAT_FormSummary <- summarise(Tortanus_EcoDAAT_bySPECIMEN_FORM,n())

`summarise()` has grouped output by 'SPECIMEN_FORM', 'MESH'. You can override using
the `.groups` argument.

#EcoDAAT data are correctly specified



#Now filter the EMA data to match the EcoDAAT data. EMA tends to double count variables from both nets, so eliminate this

#Check to see if what stages are where with EMA data

Tortanus_EMA_byGEAR_NAME <- group_by(Tortanus_EMA, MESH, GEAR_NAME)

Tortanus_EMA_GearSummary <- summarise(Tortanus_EMA_byGEAR_NAME, n())

`summarise()` has grouped output by 'MESH'. You can override using the `.groups`
argument.

#No issues with mismatched mesh and gear sizes. Need to filter for the correct stages for avoid double counts

Tortanus_EMA_60BON <- filter(Tortanus_EMA, GEAR_NAME=="60BON")

Tortanus_EMA_60BON_333 <- filter(Tortanus_EMA_60BON, MESH==333)

Tortanus_EMA_60BON_333 <- filter(Tortanus_EMA_60BON_333, STAGE_NAME=="ADULT"|STAGE_NAME=="C - 5 (COPEPODITE V)")

Tortanus_EMA_60BON_505 <- filter(Tortanus_EMA_60BON, MESH==505)

Tortanus_EMA_60BON_505 <- filter(Tortanus_EMA_60BON_505, STAGE_NAME=="ADULT"|STAGE_NAME=="C - 5 (COPEPODITE V)")



Tortanus_EMA_smallnets <- filter(Tortanus_EMA, GEAR_NAME!="60BON")


Tortanus_EMA_smallnets <- filter(Tortanus_EMA_smallnets, STAGE_NAME=="C - 4 (COPEPODITE IV)"|STAGE_NAME=="C - 3 (COPEPODITE III)"|STAGE_NAME=="C - 2 (COPEPODITE II)"|STAGE_NAME=="C - 1 (COPEPODITE I)")

#The other gears are correct, so rebuild dataset

Tortanus_EMA_Final <- rbind(Tortanus_EMA_60BON_333, Tortanus_EMA_60BON_505, Tortanus_EMA_smallnets)

ungroup(Tortanus_EMA_Final)

#Remove some files

rm(Tortanus_EMA_byGEAR_NAME,  Tortanus_EMA_smallnets, Tortanus_EMA_60BON, Tortanus_EMA_60BON_333, Tortanus_EMA_60BON_505)

#Combine into final, Tortanus data set

Tortanus <- rbind(Tortanus_EMA_Final, Tortanus_EcoDAAT)

#Add to final dataset

NBS_Zoop_Process_Final <- rbind (NBS_Zoop_Process_Final, Tortanus)

Now do biomass conversions

#NOw read in the biomass conversion data set

Biomass_annotated <- read_xlsx(here("data", "Biomass", "Biomass-Annotated.xlsx"))

#Merge the two data sets based on TAXA_COARSE, STAGE_NAME, SEX_NAME

NBS_Zoop_Process_Final <- left_join(NBS_Zoop_Process_Final, Biomass_annotated, by = c("TAXA_COARSE", "STAGE_NAME", "SEX_NAME"))

#Do some tidying to eliminate some columns

NBS_Zoop_Process_Final$NOTE <- NULL
NBS_Zoop_Process_Final$IND_WW_MG_NOTE <- NULL
NBS_Zoop_Process_Final$IND_DW_MG_CONVERTED_NOTE <- NULL
NBS_Zoop_Process_Final$IND_C_MG_CONVERTED_NOTE <- NULL
NBS_Zoop_Process_Final$GROWTH_RATE_NOTE <- NULL

#Create wet weight biomass column converted individual wet weight and abundance

NBS_Zoop_Process_Final <- mutate(NBS_Zoop_Process_Final, BIOMASS_WW_MG_M3_MEAN = IND_WW_MG_MEASURED_MEAN*EST_NUM_PERM3)

NBS_Zoop_Process_Final <- mutate(NBS_Zoop_Process_Final, BIOMASS_WW_MG_M3_SD = IND_WW_MG_MEASURED_SD*EST_NUM_PERM3)

#Create dry weight biomass column converted individual dry weight and abundance

NBS_Zoop_Process_Final <- mutate(NBS_Zoop_Process_Final, BIOMASS_DW_MG_M3_MEAN = IND_DW_MG_CONVERTED_MEAN*EST_NUM_PERM3)

NBS_Zoop_Process_Final <- mutate(NBS_Zoop_Process_Final, BIOMASS_DW_MG_M3_SD = IND_DW_MG_CONVERTED_SD*EST_NUM_PERM3)

#Create carbon weight biomass column converted individual carbon weight and abundance

NBS_Zoop_Process_Final <- mutate(NBS_Zoop_Process_Final, BIOMASS_C_MG_M3_MEAN = IND_C_MG_CONVERTED_MEAN*EST_NUM_PERM3)

NBS_Zoop_Process_Final <- mutate(NBS_Zoop_Process_Final, BIOMASS_C_MG_M3_SD = IND_C_MG_CONVERTED_SD*EST_NUM_PERM3)


#Create carbon weight biomass column converted individual carbon weight and abundance

NBS_Zoop_Process_Final <- mutate(NBS_Zoop_Process_Final, PRODUCTION_MG_C_D_MEAN = (IND_C_MG_CONVERTED_MEAN*EST_NUM_PERM3*GROWTH_RATE_MEAN)*24)

NBS_Zoop_Process_Final <- mutate(NBS_Zoop_Process_Final, PRODUCTION_MG_C_D_SD = (IND_C_MG_CONVERTED_SD*EST_NUM_PERM3*GROWTH_RATE_SD)*24)

• Add in new data (as of July 2024)

new_zoop <- read.csv("data/AllZoop_Raw_26JUL2024.csv") %>% 
             filter(YEAR> 2019,
                    !LAT<55.0473,
                    !LAT>66.1) 

Compare 2019 between both datasets to check

• Big difference is a lat longitude filter, once I add that it’s fine.

new_zoop_2019 <- read.csv("data/AllZoop_Raw_26JUL2024.csv") %>% 
             filter(YEAR %in% c(2017,2018, 2019),
                    TAXON_NAME == "Calanus marshallae",
                    !LAT<55.0473,
                    !LAT>66.1)  
  
summ_NEW_NBS <- new_zoop_2019 %>% 
    group_by(CRUISE,HAUL_ID,YEAR,MONTH,DAY,LAT,LON, DATA_SOURCE,TAXON_NAME) %>% # sum across life stages 
    dplyr::summarise(EST_NUM_PERM3 =  sum(EST_NUM_PERM3)) %>%
    filter(!LAT<58,
           !LAT>65,
           !LON> -155,
           !LON< -172,
           MONTH %in% c(7,8,9,10)) %>% 
    unite("date", c(YEAR, MONTH, DAY), sep = "/", remove = FALSE) %>%
    dplyr::mutate(date = as.Date(date, "%Y/%m/%d"),
                  DOY = yday(date),
                  TAXA_COARSE = case_when(grepl(pattern = "Themisto", x=TAXON_NAME, ignore.case = TRUE) ~ "large_zoop",
                                          grepl(pattern = "Calanus", x=TAXON_NAME, ignore.case = TRUE) ~ "large_zoop",
                                          grepl(pattern = "Copepod_large", x=TAXON_NAME, ignore.case = TRUE) ~ "large_zoop",
                                          grepl(pattern = "Neocalanus", x=TAXON_NAME, ignore.case = TRUE) ~ "large_zoop",
                                          
                                          grepl(pattern = "Cnidaria_small", x=TAXON_NAME, ignore.case = TRUE) ~ "Cnideria",
                                          grepl(pattern = "Cnidaria_large", x=TAXON_NAME, ignore.case = TRUE) ~ "Cnideria",
                                              TRUE ~ "other")) %>% 
    group_by(DATA_SOURCE,YEAR, DOY,LAT,LON) %>% # sum across species 
  dplyr::summarise(sum_EST_NUM_PERM3 = sum(EST_NUM_PERM3))  %>% 
  dplyr::mutate(YEAR = as.factor(YEAR),
         DATA_SOURCE = as.factor(DATA_SOURCE)) %>% 
  data.frame() %>% 
  group_by(YEAR) %>% 
  dplyr::summarise(mean = mean(sum_EST_NUM_PERM3))

NBS_all_2019 <- NBS_Zoop_Process_Final %>% 
             filter(YEAR== 2019,
                    TAXON_NAME == "Calanus marshallae") 



 summ_NBS <- NBS_all_2019 %>% 
    group_by(CRUISE,HAUL_ID,YEAR,MONTH,DAY,LAT,LON, DATA_SOURCE,TAXON_NAME) %>% # sum across life stages 
    dplyr::summarise(EST_NUM_PERM3 =  sum(EST_NUM_PERM3)) %>%
    filter(!LAT<58,
           !LAT>65,
           !LON> -155,
           !LON< -172,
           MONTH %in% c(7,8,9,10)) %>% 
    unite("date", c(YEAR, MONTH, DAY), sep = "/", remove = FALSE) %>%
    dplyr::mutate(date = as.Date(date, "%Y/%m/%d"),
                  DOY = yday(date),
                  TAXA_COARSE = case_when(grepl(pattern = "Themisto", x=TAXON_NAME, ignore.case = TRUE) ~ "large_zoop",
                                          grepl(pattern = "Calanus", x=TAXON_NAME, ignore.case = TRUE) ~ "large_zoop",
                                          grepl(pattern = "Copepod_large", x=TAXON_NAME, ignore.case = TRUE) ~ "large_zoop",
                                          grepl(pattern = "Neocalanus", x=TAXON_NAME, ignore.case = TRUE) ~ "large_zoop",
                                          
                                          grepl(pattern = "Cnidaria_small", x=TAXON_NAME, ignore.case = TRUE) ~ "Cnideria",
                                          grepl(pattern = "Cnidaria_large", x=TAXON_NAME, ignore.case = TRUE) ~ "Cnideria",
                                              TRUE ~ "other")) %>% 
    group_by(DATA_SOURCE,YEAR, DOY,LAT,LON) %>% # sum across species 
  dplyr::summarise(sum_EST_NUM_PERM3 = sum(EST_NUM_PERM3))  %>% 
  mutate(YEAR = as.factor(YEAR),
         DATA_SOURCE = as.factor(DATA_SOURCE)) %>% 
  data.frame()

Combine the two

combo <- rbind(new_zoop %>% 
                 dplyr::select(CRUISE, DAY, GEAR_NAME, HAUL_ID,LAT,LON,DATA_SOURCE,
                               STAGE_NAME,TAXON_NAME, YEAR,MONTH,EST_NUM_PERM3),
               NBS_Zoop_Process_Final %>% 
                 dplyr::select(CRUISE, DAY, GEAR_NAME, HAUL_ID,LAT,LON,DATA_SOURCE,
                               STAGE_NAME,TAXON_NAME,YEAR,MONTH,EST_NUM_PERM3))

write.csv(combo, here("data", "Processed_Data", "NBS_Zoop_Process_Final.csv"), row.names = FALSE)